© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 27946
    Prev
    Next
    INDEX
    Explanations

    transparency and argument parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diathermy
    0.49
     ؛
    0.49
    ]
    0.49
     charme
    0.48
    ++;
    0.45
     formidable
    0.45
    発行
    0.45
    ]}
    0.44
     keenly
    0.44
    ጣት
    0.44
    POSITIVE LOGITS
     বিষয়ের
    0.60
     Air
    0.59
    ப்படுகிறது
    0.58
     Tú
    0.57
    نسب
    0.56
     relativo
    0.55
     Aircraft
    0.55
     tú
    0.54
     Chess
    0.54
    ților
    0.53
    Activations Density 0.000%

    No Known Activations